WEBVTT Kind: captions Language: en 00:00:00.640 --> 00:00:02.710 align:start position:0% empirical studies typically need to 00:00:02.710 --> 00:00:02.720 align:start position:0% empirical studies typically need to 00:00:02.720 --> 00:00:04.230 align:start position:0% empirical studies typically need to demonstrate reliability 00:00:04.230 --> 00:00:04.240 align:start position:0% demonstrate reliability 00:00:04.240 --> 00:00:06.710 align:start position:0% demonstrate reliability and validity of their measures the two 00:00:06.710 --> 00:00:06.720 align:start position:0% and validity of their measures the two 00:00:06.720 --> 00:00:09.110 align:start position:0% and validity of their measures the two commonly used tools for doing so 00:00:09.110 --> 00:00:09.120 align:start position:0% commonly used tools for doing so 00:00:09.120 --> 00:00:11.830 align:start position:0% commonly used tools for doing so is factor analysis for validation and 00:00:11.830 --> 00:00:11.840 align:start position:0% is factor analysis for validation and 00:00:11.840 --> 00:00:13.270 align:start position:0% is factor analysis for validation and coefficient alpha 00:00:13.270 --> 00:00:13.280 align:start position:0% coefficient alpha 00:00:13.280 --> 00:00:15.669 align:start position:0% coefficient alpha for demonstrating reliability there are 00:00:15.669 --> 00:00:15.679 align:start position:0% for demonstrating reliability there are 00:00:15.679 --> 00:00:17.349 align:start position:0% for demonstrating reliability there are also other techniques that cannot be 00:00:17.349 --> 00:00:17.359 align:start position:0% also other techniques that cannot be 00:00:17.359 --> 00:00:18.070 align:start position:0% also other techniques that cannot be applied 00:00:18.070 --> 00:00:18.080 align:start position:0% applied 00:00:18.080 --> 00:00:20.310 align:start position:0% applied but these are the most commonly used one 00:00:20.310 --> 00:00:20.320 align:start position:0% but these are the most commonly used one 00:00:20.320 --> 00:00:22.790 align:start position:0% but these are the most commonly used one and these are also the easiest to apply 00:00:22.790 --> 00:00:22.800 align:start position:0% and these are also the easiest to apply 00:00:22.800 --> 00:00:24.870 align:start position:0% and these are also the easiest to apply let's take a look at empirical example 00:00:24.870 --> 00:00:24.880 align:start position:0% let's take a look at empirical example 00:00:24.880 --> 00:00:26.630 align:start position:0% let's take a look at empirical example our example comes from baron 00:00:26.630 --> 00:00:26.640 align:start position:0% our example comes from baron 00:00:26.640 --> 00:00:29.669 align:start position:0% our example comes from baron and tang and they 00:00:29.669 --> 00:00:29.679 align:start position:0% and tang and they 00:00:29.679 --> 00:00:32.630 align:start position:0% and tang and they uh measure social skills and of 00:00:32.630 --> 00:00:32.640 align:start position:0% uh measure social skills and of 00:00:32.640 --> 00:00:33.670 align:start position:0% uh measure social skills and of entrepreneurs 00:00:33.670 --> 00:00:33.680 align:start position:0% entrepreneurs 00:00:33.680 --> 00:00:35.350 align:start position:0% entrepreneurs and here we can see that they are saying 00:00:35.350 --> 00:00:35.360 align:start position:0% and here we can see that they are saying 00:00:35.360 --> 00:00:37.190 align:start position:0% and here we can see that they are saying that they apply 00:00:37.190 --> 00:00:37.200 align:start position:0% that they apply 00:00:37.200 --> 00:00:39.430 align:start position:0% that they apply alpha so there's the alpha character for 00:00:39.430 --> 00:00:39.440 align:start position:0% alpha so there's the alpha character for 00:00:39.440 --> 00:00:40.950 align:start position:0% alpha so there's the alpha character for reliability assessment 00:00:40.950 --> 00:00:40.960 align:start position:0% reliability assessment 00:00:40.960 --> 00:00:44.470 align:start position:0% reliability assessment they present some numbers 0.85.71 00:00:44.470 --> 00:00:44.480 align:start position:0% they present some numbers 0.85.71 00:00:44.480 --> 00:00:46.150 align:start position:0% they present some numbers 0.85.71 and they also report that they applied 00:00:46.150 --> 00:00:46.160 align:start position:0% and they also report that they applied 00:00:46.160 --> 00:00:48.389 align:start position:0% and they also report that they applied factor analysis so so what do these two 00:00:48.389 --> 00:00:48.399 align:start position:0% factor analysis so so what do these two 00:00:48.399 --> 00:00:49.590 align:start position:0% factor analysis so so what do these two techniques do 00:00:49.590 --> 00:00:49.600 align:start position:0% techniques do 00:00:49.600 --> 00:00:52.470 align:start position:0% techniques do and why are they used and used here what 00:00:52.470 --> 00:00:52.480 align:start position:0% and why are they used and used here what 00:00:52.480 --> 00:00:54.310 align:start position:0% and why are they used and used here what is the logic 00:00:54.310 --> 00:00:54.320 align:start position:0% is the logic 00:00:54.320 --> 00:00:56.709 align:start position:0% is the logic also what does this table mean so this 00:00:56.709 --> 00:00:56.719 align:start position:0% also what does this table mean so this 00:00:56.719 --> 00:00:59.189 align:start position:0% also what does this table mean so this table shows the factor analysis results 00:00:59.189 --> 00:00:59.199 align:start position:0% table shows the factor analysis results 00:00:59.199 --> 00:01:01.430 align:start position:0% table shows the factor analysis results and it also shows us the alphas that 00:01:01.430 --> 00:01:01.440 align:start position:0% and it also shows us the alphas that 00:01:01.440 --> 00:01:03.910 align:start position:0% and it also shows us the alphas that they were calculating for this case 00:01:03.910 --> 00:01:03.920 align:start position:0% they were calculating for this case 00:01:03.920 --> 00:01:07.109 align:start position:0% they were calculating for this case to understand what this table is about 00:01:07.109 --> 00:01:07.119 align:start position:0% to understand what this table is about 00:01:07.119 --> 00:01:09.590 align:start position:0% to understand what this table is about we need to first understand a bit about 00:01:09.590 --> 00:01:09.600 align:start position:0% we need to first understand a bit about 00:01:09.600 --> 00:01:10.870 align:start position:0% we need to first understand a bit about measurement 00:01:10.870 --> 00:01:10.880 align:start position:0% measurement 00:01:10.880 --> 00:01:13.270 align:start position:0% measurement and what is reliability so let's assume 00:01:13.270 --> 00:01:13.280 align:start position:0% and what is reliability so let's assume 00:01:13.280 --> 00:01:14.789 align:start position:0% and what is reliability so let's assume that we have this bathroom scale here 00:01:14.789 --> 00:01:14.799 align:start position:0% that we have this bathroom scale here 00:01:14.799 --> 00:01:15.990 align:start position:0% that we have this bathroom scale here it's a bit rusty 00:01:15.990 --> 00:01:16.000 align:start position:0% it's a bit rusty 00:01:16.000 --> 00:01:17.910 align:start position:0% it's a bit rusty we don't know whether it is reliable or 00:01:17.910 --> 00:01:17.920 align:start position:0% we don't know whether it is reliable or 00:01:17.920 --> 00:01:20.070 align:start position:0% we don't know whether it is reliable or not to determine if the scale is 00:01:20.070 --> 00:01:20.080 align:start position:0% not to determine if the scale is 00:01:20.080 --> 00:01:22.149 align:start position:0% not to determine if the scale is reliable if it always gives the same 00:01:22.149 --> 00:01:22.159 align:start position:0% reliable if it always gives the same 00:01:22.159 --> 00:01:23.910 align:start position:0% reliable if it always gives the same result when you step on in 00:01:23.910 --> 00:01:23.920 align:start position:0% result when you step on in 00:01:23.920 --> 00:01:26.710 align:start position:0% result when you step on in step on it it's very easy to check by 00:01:26.710 --> 00:01:26.720 align:start position:0% step on it it's very easy to check by 00:01:26.720 --> 00:01:27.429 align:start position:0% step on it it's very easy to check by simply 00:01:27.429 --> 00:01:27.439 align:start position:0% simply 00:01:27.439 --> 00:01:30.230 align:start position:0% simply stepping on the scale once getting the 00:01:30.230 --> 00:01:30.240 align:start position:0% stepping on the scale once getting the 00:01:30.240 --> 00:01:30.870 align:start position:0% stepping on the scale once getting the reading 00:01:30.870 --> 00:01:30.880 align:start position:0% reading 00:01:30.880 --> 00:01:34.230 align:start position:0% reading stepping off letting the scale to reset 00:01:34.230 --> 00:01:34.240 align:start position:0% stepping off letting the scale to reset 00:01:34.240 --> 00:01:37.109 align:start position:0% stepping off letting the scale to reset then stepping on the scale again getting 00:01:37.109 --> 00:01:37.119 align:start position:0% then stepping on the scale again getting 00:01:37.119 --> 00:01:37.910 align:start position:0% then stepping on the scale again getting the reading 00:01:37.910 --> 00:01:37.920 align:start position:0% the reading 00:01:37.920 --> 00:01:40.710 align:start position:0% the reading stepping off letting it reset stepping 00:01:40.710 --> 00:01:40.720 align:start position:0% stepping off letting it reset stepping 00:01:40.720 --> 00:01:41.030 align:start position:0% stepping off letting it reset stepping it 00:01:41.030 --> 00:01:41.040 align:start position:0% it 00:01:41.040 --> 00:01:42.950 align:start position:0% it or getting it on getting the reading and 00:01:42.950 --> 00:01:42.960 align:start position:0% or getting it on getting the reading and 00:01:42.960 --> 00:01:44.069 align:start position:0% or getting it on getting the reading and stepping off 00:01:44.069 --> 00:01:44.079 align:start position:0% stepping off 00:01:44.079 --> 00:01:46.149 align:start position:0% stepping off now you have three different readings 00:01:46.149 --> 00:01:46.159 align:start position:0% now you have three different readings 00:01:46.159 --> 00:01:47.590 align:start position:0% now you have three different readings from the same scale 00:01:47.590 --> 00:01:47.600 align:start position:0% from the same scale 00:01:47.600 --> 00:01:50.630 align:start position:0% from the same scale if those all three readings are the same 00:01:50.630 --> 00:01:50.640 align:start position:0% if those all three readings are the same 00:01:50.640 --> 00:01:53.270 align:start position:0% if those all three readings are the same or very similar to one another then we 00:01:53.270 --> 00:01:53.280 align:start position:0% or very similar to one another then we 00:01:53.280 --> 00:01:54.469 align:start position:0% or very similar to one another then we conclude that this 00:01:54.469 --> 00:01:54.479 align:start position:0% conclude that this 00:01:54.479 --> 00:01:57.590 align:start position:0% conclude that this scale is reliable it lacks 00:01:57.590 --> 00:01:57.600 align:start position:0% scale is reliable it lacks 00:01:57.600 --> 00:02:00.310 align:start position:0% scale is reliable it lacks any random error it of course does not 00:02:00.310 --> 00:02:00.320 align:start position:0% any random error it of course does not 00:02:00.320 --> 00:02:02.230 align:start position:0% any random error it of course does not tell us if it's a valid scale it might 00:02:02.230 --> 00:02:02.240 align:start position:0% tell us if it's a valid scale it might 00:02:02.240 --> 00:02:04.630 align:start position:0% tell us if it's a valid scale it might show 10 kilos too much or 10 kilos to 00:02:04.630 --> 00:02:04.640 align:start position:0% show 10 kilos too much or 10 kilos to 00:02:04.640 --> 00:02:05.109 align:start position:0% show 10 kilos too much or 10 kilos to liter 00:02:05.109 --> 00:02:05.119 align:start position:0% liter 00:02:05.119 --> 00:02:07.749 align:start position:0% liter little but that's not the question that 00:02:07.749 --> 00:02:07.759 align:start position:0% little but that's not the question that 00:02:07.759 --> 00:02:10.070 align:start position:0% little but that's not the question that reliability addresses so reliability is 00:02:10.070 --> 00:02:10.080 align:start position:0% reliability addresses so reliability is 00:02:10.080 --> 00:02:11.589 align:start position:0% reliability addresses so reliability is about consistency 00:02:11.589 --> 00:02:11.599 align:start position:0% about consistency 00:02:11.599 --> 00:02:13.589 align:start position:0% about consistency if we measure the same thing again and 00:02:13.589 --> 00:02:13.599 align:start position:0% if we measure the same thing again and 00:02:13.599 --> 00:02:15.830 align:start position:0% if we measure the same thing again and again do we get the same result 00:02:15.830 --> 00:02:15.840 align:start position:0% again do we get the same result 00:02:15.840 --> 00:02:18.229 align:start position:0% again do we get the same result so how do we do that when we measure 00:02:18.229 --> 00:02:18.239 align:start position:0% so how do we do that when we measure 00:02:18.239 --> 00:02:19.110 align:start position:0% so how do we do that when we measure people 00:02:19.110 --> 00:02:19.120 align:start position:0% people 00:02:19.120 --> 00:02:21.030 align:start position:0% people if we want to measure a person's social 00:02:21.030 --> 00:02:21.040 align:start position:0% if we want to measure a person's social 00:02:21.040 --> 00:02:22.150 align:start position:0% if we want to measure a person's social perception 00:02:22.150 --> 00:02:22.160 align:start position:0% perception 00:02:22.160 --> 00:02:24.550 align:start position:0% perception then we can't simply ask the same 00:02:24.550 --> 00:02:24.560 align:start position:0% then we can't simply ask the same 00:02:24.560 --> 00:02:26.470 align:start position:0% then we can't simply ask the same question again and again 00:02:26.470 --> 00:02:26.480 align:start position:0% question again and again 00:02:26.480 --> 00:02:28.470 align:start position:0% question again and again because a person will remember what they 00:02:28.470 --> 00:02:28.480 align:start position:0% because a person will remember what they 00:02:28.480 --> 00:02:30.070 align:start position:0% because a person will remember what they asked for the previous time 00:02:30.070 --> 00:02:30.080 align:start position:0% asked for the previous time 00:02:30.080 --> 00:02:32.150 align:start position:0% asked for the previous time and then they will just repeat what they 00:02:32.150 --> 00:02:32.160 align:start position:0% and then they will just repeat what they 00:02:32.160 --> 00:02:33.350 align:start position:0% and then they will just repeat what they answered so 00:02:33.350 --> 00:02:33.360 align:start position:0% answered so 00:02:33.360 --> 00:02:35.910 align:start position:0% answered so it doesn't work so people don't reset as 00:02:35.910 --> 00:02:35.920 align:start position:0% it doesn't work so people don't reset as 00:02:35.920 --> 00:02:37.190 align:start position:0% it doesn't work so people don't reset as easily as scales 00:02:37.190 --> 00:02:37.200 align:start position:0% easily as scales 00:02:37.200 --> 00:02:41.190 align:start position:0% easily as scales do bathroom scales in practice 00:02:41.190 --> 00:02:41.200 align:start position:0% do bathroom scales in practice 00:02:41.200 --> 00:02:43.270 align:start position:0% do bathroom scales in practice we often use multiple different 00:02:43.270 --> 00:02:43.280 align:start position:0% we often use multiple different 00:02:43.280 --> 00:02:44.390 align:start position:0% we often use multiple different questions 00:02:44.390 --> 00:02:44.400 align:start position:0% questions 00:02:44.400 --> 00:02:47.670 align:start position:0% questions that are called distinct measures so we 00:02:47.670 --> 00:02:47.680 align:start position:0% that are called distinct measures so we 00:02:47.680 --> 00:02:49.509 align:start position:0% that are called distinct measures so we have five different questions 00:02:49.509 --> 00:02:49.519 align:start position:0% have five different questions 00:02:49.519 --> 00:02:51.430 align:start position:0% have five different questions that are all supposed to measure the 00:02:51.430 --> 00:02:51.440 align:start position:0% that are all supposed to measure the 00:02:51.440 --> 00:02:53.670 align:start position:0% that are all supposed to measure the same thing but they are sufficiently 00:02:53.670 --> 00:02:53.680 align:start position:0% same thing but they are sufficiently 00:02:53.680 --> 00:02:54.390 align:start position:0% same thing but they are sufficiently distinct 00:02:54.390 --> 00:02:54.400 align:start position:0% distinct 00:02:54.400 --> 00:02:56.070 align:start position:0% distinct so that the person doesn't really 00:02:56.070 --> 00:02:56.080 align:start position:0% so that the person doesn't really 00:02:56.080 --> 00:02:58.229 align:start position:0% so that the person doesn't really recognize that these are actually asking 00:02:58.229 --> 00:02:58.239 align:start position:0% recognize that these are actually asking 00:02:58.239 --> 00:02:59.670 align:start position:0% recognize that these are actually asking about the same thing 00:02:59.670 --> 00:02:59.680 align:start position:0% about the same thing 00:02:59.680 --> 00:03:01.990 align:start position:0% about the same thing about persons social perception 00:03:01.990 --> 00:03:02.000 align:start position:0% about persons social perception 00:03:02.000 --> 00:03:03.670 align:start position:0% about persons social perception capabilities 00:03:03.670 --> 00:03:03.680 align:start position:0% capabilities 00:03:03.680 --> 00:03:06.550 align:start position:0% capabilities they are nevertheless sufficiently 00:03:06.550 --> 00:03:06.560 align:start position:0% they are nevertheless sufficiently 00:03:06.560 --> 00:03:07.270 align:start position:0% they are nevertheless sufficiently similar 00:03:07.270 --> 00:03:07.280 align:start position:0% similar 00:03:07.280 --> 00:03:09.030 align:start position:0% similar that we can argue that they all measure 00:03:09.030 --> 00:03:09.040 align:start position:0% that we can argue that they all measure 00:03:09.040 --> 00:03:11.110 align:start position:0% that we can argue that they all measure the same thing and and this is a fine 00:03:11.110 --> 00:03:11.120 align:start position:0% the same thing and and this is a fine 00:03:11.120 --> 00:03:13.589 align:start position:0% the same thing and and this is a fine balance on how different and how similar 00:03:13.589 --> 00:03:13.599 align:start position:0% balance on how different and how similar 00:03:13.599 --> 00:03:16.229 align:start position:0% balance on how different and how similar the items can be there is also another 00:03:16.229 --> 00:03:16.239 align:start position:0% the items can be there is also another 00:03:16.239 --> 00:03:17.030 align:start position:0% the items can be there is also another strategy 00:03:17.030 --> 00:03:17.040 align:start position:0% strategy 00:03:17.040 --> 00:03:19.509 align:start position:0% strategy for assessing reliability called test 00:03:19.509 --> 00:03:19.519 align:start position:0% for assessing reliability called test 00:03:19.519 --> 00:03:21.030 align:start position:0% for assessing reliability called test retest reliability 00:03:21.030 --> 00:03:21.040 align:start position:0% retest reliability 00:03:21.040 --> 00:03:23.509 align:start position:0% retest reliability where we actually ask the same question 00:03:23.509 --> 00:03:23.519 align:start position:0% where we actually ask the same question 00:03:23.519 --> 00:03:24.550 align:start position:0% where we actually ask the same question over and over 00:03:24.550 --> 00:03:24.560 align:start position:0% over and over 00:03:24.560 --> 00:03:26.710 align:start position:0% over and over with a time delay but this is a bit 00:03:26.710 --> 00:03:26.720 align:start position:0% with a time delay but this is a bit 00:03:26.720 --> 00:03:28.949 align:start position:0% with a time delay but this is a bit problematic because the time delay 00:03:28.949 --> 00:03:28.959 align:start position:0% problematic because the time delay 00:03:28.959 --> 00:03:31.430 align:start position:0% problematic because the time delay for asking a question for from a person 00:03:31.430 --> 00:03:31.440 align:start position:0% for asking a question for from a person 00:03:31.440 --> 00:03:33.350 align:start position:0% for asking a question for from a person needs to be days or weeks 00:03:33.350 --> 00:03:33.360 align:start position:0% needs to be days or weeks 00:03:33.360 --> 00:03:35.190 align:start position:0% needs to be days or weeks or otherwise the person will remember 00:03:35.190 --> 00:03:35.200 align:start position:0% or otherwise the person will remember 00:03:35.200 --> 00:03:36.470 align:start position:0% or otherwise the person will remember their past answer 00:03:36.470 --> 00:03:36.480 align:start position:0% their past answer 00:03:36.480 --> 00:03:38.470 align:start position:0% their past answer and we'll just repeat it without 00:03:38.470 --> 00:03:38.480 align:start position:0% and we'll just repeat it without 00:03:38.480 --> 00:03:40.309 align:start position:0% and we'll just repeat it without reconsidering the question 00:03:40.309 --> 00:03:40.319 align:start position:0% reconsidering the question 00:03:40.319 --> 00:03:42.789 align:start position:0% reconsidering the question so in practice most studies use these 00:03:42.789 --> 00:03:42.799 align:start position:0% so in practice most studies use these 00:03:42.799 --> 00:03:44.869 align:start position:0% so in practice most studies use these distinct measures we asked 00:03:44.869 --> 00:03:44.879 align:start position:0% distinct measures we asked 00:03:44.879 --> 00:03:47.430 align:start position:0% distinct measures we asked for example three or five different 00:03:47.430 --> 00:03:47.440 align:start position:0% for example three or five different 00:03:47.440 --> 00:03:49.110 align:start position:0% for example three or five different questions that are supposed to measure 00:03:49.110 --> 00:03:49.120 align:start position:0% questions that are supposed to measure 00:03:49.120 --> 00:03:49.910 align:start position:0% questions that are supposed to measure the same thing 00:03:49.910 --> 00:03:49.920 align:start position:0% the same thing 00:03:49.920 --> 00:03:51.350 align:start position:0% the same thing but they're different enough that the 00:03:51.350 --> 00:03:51.360 align:start position:0% but they're different enough that the 00:03:51.360 --> 00:03:53.030 align:start position:0% but they're different enough that the person doesn't realize that they're 00:03:53.030 --> 00:03:53.040 align:start position:0% person doesn't realize that they're 00:03:53.040 --> 00:03:55.110 align:start position:0% person doesn't realize that they're being asked the same thing 00:03:55.110 --> 00:03:55.120 align:start position:0% being asked the same thing 00:03:55.120 --> 00:03:57.670 align:start position:0% being asked the same thing factor analysis is a tool for validating 00:03:57.670 --> 00:03:57.680 align:start position:0% factor analysis is a tool for validating 00:03:57.680 --> 00:03:59.350 align:start position:0% factor analysis is a tool for validating these multiple item measures 00:03:59.350 --> 00:03:59.360 align:start position:0% these multiple item measures 00:03:59.360 --> 00:04:01.350 align:start position:0% these multiple item measures this is a table of factory analysis 00:04:01.350 --> 00:04:01.360 align:start position:0% this is a table of factory analysis 00:04:01.360 --> 00:04:02.390 align:start position:0% this is a table of factory analysis results 00:04:02.390 --> 00:04:02.400 align:start position:0% results 00:04:02.400 --> 00:04:04.470 align:start position:0% results and what these results tell us or what 00:04:04.470 --> 00:04:04.480 align:start position:0% and what these results tell us or what 00:04:04.480 --> 00:04:06.390 align:start position:0% and what these results tell us or what factor analysis tells us 00:04:06.390 --> 00:04:06.400 align:start position:0% factor analysis tells us 00:04:06.400 --> 00:04:09.270 align:start position:0% factor analysis tells us that it tells which items go together 00:04:09.270 --> 00:04:09.280 align:start position:0% that it tells which items go together 00:04:09.280 --> 00:04:09.670 align:start position:0% that it tells which items go together which 00:04:09.670 --> 00:04:09.680 align:start position:0% which 00:04:09.680 --> 00:04:12.070 align:start position:0% which items have something in common or if 00:04:12.070 --> 00:04:12.080 align:start position:0% items have something in common or if 00:04:12.080 --> 00:04:13.750 align:start position:0% items have something in common or if there are any underlying dimensions in 00:04:13.750 --> 00:04:13.760 align:start position:0% there are any underlying dimensions in 00:04:13.760 --> 00:04:14.630 align:start position:0% there are any underlying dimensions in the data 00:04:14.630 --> 00:04:14.640 align:start position:0% the data 00:04:14.640 --> 00:04:16.629 align:start position:0% the data so the idea of factor analysis here is 00:04:16.629 --> 00:04:16.639 align:start position:0% so the idea of factor analysis here is 00:04:16.639 --> 00:04:17.670 align:start position:0% so the idea of factor analysis here is that if we have five 00:04:17.670 --> 00:04:17.680 align:start position:0% that if we have five 00:04:17.680 --> 00:04:20.710 align:start position:0% that if we have five measurement scales then uh 00:04:20.710 --> 00:04:20.720 align:start position:0% measurement scales then uh 00:04:20.720 --> 00:04:22.950 align:start position:0% measurement scales then uh these items should be grouped 00:04:22.950 --> 00:04:22.960 align:start position:0% these items should be grouped 00:04:22.960 --> 00:04:23.830 align:start position:0% these items should be grouped empirically 00:04:23.830 --> 00:04:23.840 align:start position:0% empirically 00:04:23.840 --> 00:04:25.189 align:start position:0% empirically according to the things that they're 00:04:25.189 --> 00:04:25.199 align:start position:0% according to the things that they're 00:04:25.199 --> 00:04:27.590 align:start position:0% according to the things that they're supposed to measure so these file items 00:04:27.590 --> 00:04:27.600 align:start position:0% supposed to measure so these file items 00:04:27.600 --> 00:04:28.950 align:start position:0% supposed to measure so these file items are supposed to mess with social 00:04:28.950 --> 00:04:28.960 align:start position:0% are supposed to mess with social 00:04:28.960 --> 00:04:29.830 align:start position:0% are supposed to mess with social perception 00:04:29.830 --> 00:04:29.840 align:start position:0% perception 00:04:29.840 --> 00:04:32.390 align:start position:0% perception so we say that uh conceptually they have 00:04:32.390 --> 00:04:32.400 align:start position:0% so we say that uh conceptually they have 00:04:32.400 --> 00:04:34.150 align:start position:0% so we say that uh conceptually they have in common that they all measure social 00:04:34.150 --> 00:04:34.160 align:start position:0% in common that they all measure social 00:04:34.160 --> 00:04:35.110 align:start position:0% in common that they all measure social perceptions 00:04:35.110 --> 00:04:35.120 align:start position:0% perceptions 00:04:35.120 --> 00:04:36.790 align:start position:0% perceptions then we look at do they something do 00:04:36.790 --> 00:04:36.800 align:start position:0% then we look at do they something do 00:04:36.800 --> 00:04:38.230 align:start position:0% then we look at do they something do they have something in common also 00:04:38.230 --> 00:04:38.240 align:start position:0% they have something in common also 00:04:38.240 --> 00:04:39.110 align:start position:0% they have something in common also empirically 00:04:39.110 --> 00:04:39.120 align:start position:0% empirically 00:04:39.120 --> 00:04:42.230 align:start position:0% empirically and factor analysis does that for us so 00:04:42.230 --> 00:04:42.240 align:start position:0% and factor analysis does that for us so 00:04:42.240 --> 00:04:44.150 align:start position:0% and factor analysis does that for us so factor analysis identifies 00:04:44.150 --> 00:04:44.160 align:start position:0% factor analysis identifies 00:04:44.160 --> 00:04:46.469 align:start position:0% factor analysis identifies that these five items belong to factor 00:04:46.469 --> 00:04:46.479 align:start position:0% that these five items belong to factor 00:04:46.479 --> 00:04:47.670 align:start position:0% that these five items belong to factor number two 00:04:47.670 --> 00:04:47.680 align:start position:0% number two 00:04:47.680 --> 00:04:50.550 align:start position:0% number two so when we look at this table we want to 00:04:50.550 --> 00:04:50.560 align:start position:0% so when we look at this table we want to 00:04:50.560 --> 00:04:52.070 align:start position:0% so when we look at this table we want to see a pattern like this 00:04:52.070 --> 00:04:52.080 align:start position:0% see a pattern like this 00:04:52.080 --> 00:04:55.270 align:start position:0% see a pattern like this so each item belongs to one factor these 00:04:55.270 --> 00:04:55.280 align:start position:0% so each item belongs to one factor these 00:04:55.280 --> 00:04:55.990 align:start position:0% so each item belongs to one factor these numbers are called 00:04:55.990 --> 00:04:56.000 align:start position:0% numbers are called 00:04:56.000 --> 00:04:58.629 align:start position:0% numbers are called factor loadings ideally the loading on 00:04:58.629 --> 00:04:58.639 align:start position:0% factor loadings ideally the loading on 00:04:58.639 --> 00:05:01.189 align:start position:0% factor loadings ideally the loading on the main factor would be more than 0.7 00:05:01.189 --> 00:05:01.199 align:start position:0% the main factor would be more than 0.7 00:05:01.199 --> 00:05:04.629 align:start position:0% the main factor would be more than 0.7 this 0.5 is a bit weak so 0.7 is 00:05:04.629 --> 00:05:04.639 align:start position:0% this 0.5 is a bit weak so 0.7 is 00:05:04.639 --> 00:05:06.790 align:start position:0% this 0.5 is a bit weak so 0.7 is typically acceptable reliability for 00:05:06.790 --> 00:05:06.800 align:start position:0% typically acceptable reliability for 00:05:06.800 --> 00:05:07.830 align:start position:0% typically acceptable reliability for that item 00:05:07.830 --> 00:05:07.840 align:start position:0% that item 00:05:07.840 --> 00:05:10.310 align:start position:0% that item we also want to see that the items don't 00:05:10.310 --> 00:05:10.320 align:start position:0% we also want to see that the items don't 00:05:10.320 --> 00:05:12.870 align:start position:0% we also want to see that the items don't load highly on the other factors 00:05:12.870 --> 00:05:12.880 align:start position:0% load highly on the other factors 00:05:12.880 --> 00:05:15.110 align:start position:0% load highly on the other factors so if we assume that this factor 3 for 00:05:15.110 --> 00:05:15.120 align:start position:0% so if we assume that this factor 3 for 00:05:15.120 --> 00:05:16.790 align:start position:0% so if we assume that this factor 3 for example is expressiveness 00:05:16.790 --> 00:05:16.800 align:start position:0% example is expressiveness 00:05:16.800 --> 00:05:18.790 align:start position:0% example is expressiveness so these items correlate strongly 00:05:18.790 --> 00:05:18.800 align:start position:0% so these items correlate strongly 00:05:18.800 --> 00:05:20.629 align:start position:0% so these items correlate strongly because they all measure expressiveness 00:05:20.629 --> 00:05:20.639 align:start position:0% because they all measure expressiveness 00:05:20.639 --> 00:05:22.950 align:start position:0% because they all measure expressiveness we want to see low values here in the 00:05:22.950 --> 00:05:22.960 align:start position:0% we want to see low values here in the 00:05:22.960 --> 00:05:24.870 align:start position:0% we want to see low values here in the social perception items these social 00:05:24.870 --> 00:05:24.880 align:start position:0% social perception items these social 00:05:24.880 --> 00:05:26.390 align:start position:0% social perception items these social perception items should not 00:05:26.390 --> 00:05:26.400 align:start position:0% perception items should not 00:05:26.400 --> 00:05:28.550 align:start position:0% perception items should not depend on expressiveness and this is a 00:05:28.550 --> 00:05:28.560 align:start position:0% depend on expressiveness and this is a 00:05:28.560 --> 00:05:30.390 align:start position:0% depend on expressiveness and this is a very clean factor solution 00:05:30.390 --> 00:05:30.400 align:start position:0% very clean factor solution 00:05:30.400 --> 00:05:33.029 align:start position:0% very clean factor solution because the social perception items only 00:05:33.029 --> 00:05:33.039 align:start position:0% because the social perception items only 00:05:33.039 --> 00:05:34.230 align:start position:0% because the social perception items only load on the source 00:05:34.230 --> 00:05:34.240 align:start position:0% load on the source 00:05:34.240 --> 00:05:37.990 align:start position:0% load on the source perception factor but not the others so 00:05:37.990 --> 00:05:38.000 align:start position:0% perception factor but not the others so 00:05:38.000 --> 00:05:39.990 align:start position:0% perception factor but not the others so we want to see that these are small 00:05:39.990 --> 00:05:40.000 align:start position:0% we want to see that these are small 00:05:40.000 --> 00:05:41.990 align:start position:0% we want to see that these are small and the main loadings are large what is 00:05:41.990 --> 00:05:42.000 align:start position:0% and the main loadings are large what is 00:05:42.000 --> 00:05:43.350 align:start position:0% and the main loadings are large what is small 00:05:43.350 --> 00:05:43.360 align:start position:0% small 00:05:43.360 --> 00:05:45.670 align:start position:0% small less than 0.2 less than 0.3 depending on 00:05:45.670 --> 00:05:45.680 align:start position:0% less than 0.2 less than 0.3 depending on 00:05:45.680 --> 00:05:48.310 align:start position:0% less than 0.2 less than 0.3 depending on the source is typically considered small 00:05:48.310 --> 00:05:48.320 align:start position:0% the source is typically considered small 00:05:48.320 --> 00:05:50.629 align:start position:0% the source is typically considered small not all the items work ideally for 00:05:50.629 --> 00:05:50.639 align:start position:0% not all the items work ideally for 00:05:50.639 --> 00:05:52.390 align:start position:0% not all the items work ideally for example this item here 00:05:52.390 --> 00:05:52.400 align:start position:0% example this item here 00:05:52.400 --> 00:05:54.230 align:start position:0% example this item here people tell me that i'm a sensitive and 00:05:54.230 --> 00:05:54.240 align:start position:0% people tell me that i'm a sensitive and 00:05:54.240 --> 00:05:55.830 align:start position:0% people tell me that i'm a sensitive and understanding person 00:05:55.830 --> 00:05:55.840 align:start position:0% understanding person 00:05:55.840 --> 00:05:59.909 align:start position:0% understanding person is loading on factor four and and factor 00:05:59.909 --> 00:05:59.919 align:start position:0% is loading on factor four and and factor 00:05:59.919 --> 00:06:03.350 align:start position:0% is loading on factor four and and factor three and factor one so it's not cleanly 00:06:03.350 --> 00:06:03.360 align:start position:0% three and factor one so it's not cleanly 00:06:03.360 --> 00:06:05.990 align:start position:0% three and factor one so it's not cleanly measuring only factor five which is 00:06:05.990 --> 00:06:06.000 align:start position:0% measuring only factor five which is 00:06:06.000 --> 00:06:06.870 align:start position:0% measuring only factor five which is social adapt 00:06:06.870 --> 00:06:06.880 align:start position:0% social adapt 00:06:06.880 --> 00:06:09.670 align:start position:0% social adapt by adaptability but it also depends on 00:06:09.670 --> 00:06:09.680 align:start position:0% by adaptability but it also depends on 00:06:09.680 --> 00:06:11.189 align:start position:0% by adaptability but it also depends on for example uh 00:06:11.189 --> 00:06:11.199 align:start position:0% for example uh 00:06:11.199 --> 00:06:13.909 align:start position:0% for example uh expressiveness so that kind of items we 00:06:13.909 --> 00:06:13.919 align:start position:0% expressiveness so that kind of items we 00:06:13.919 --> 00:06:15.350 align:start position:0% expressiveness so that kind of items we might consider dropping 00:06:15.350 --> 00:06:15.360 align:start position:0% might consider dropping 00:06:15.360 --> 00:06:17.270 align:start position:0% might consider dropping but it was retained in this study 00:06:17.270 --> 00:06:17.280 align:start position:0% but it was retained in this study 00:06:17.280 --> 00:06:18.950 align:start position:0% but it was retained in this study because it was have been validated 00:06:18.950 --> 00:06:18.960 align:start position:0% because it was have been validated 00:06:18.960 --> 00:06:19.670 align:start position:0% because it was have been validated before 00:06:19.670 --> 00:06:19.680 align:start position:0% before 00:06:19.680 --> 00:06:21.510 align:start position:0% before so this is factor analysis you look for 00:06:21.510 --> 00:06:21.520 align:start position:0% so this is factor analysis you look for 00:06:21.520 --> 00:06:23.110 align:start position:0% so this is factor analysis you look for pattern where each 00:06:23.110 --> 00:06:23.120 align:start position:0% pattern where each 00:06:23.120 --> 00:06:24.870 align:start position:0% pattern where each item loads on the same that they are 00:06:24.870 --> 00:06:24.880 align:start position:0% item loads on the same that they are 00:06:24.880 --> 00:06:26.629 align:start position:0% item loads on the same that they are supposed to measure the same thing 00:06:26.629 --> 00:06:26.639 align:start position:0% supposed to measure the same thing 00:06:26.639 --> 00:06:28.790 align:start position:0% supposed to measure the same thing loads on the same factor and not on any 00:06:28.790 --> 00:06:28.800 align:start position:0% loads on the same factor and not on any 00:06:28.800 --> 00:06:29.749 align:start position:0% loads on the same factor and not on any other factors 00:06:29.749 --> 00:06:29.759 align:start position:0% other factors 00:06:29.759 --> 00:06:31.350 align:start position:0% other factors then we would typically label these 00:06:31.350 --> 00:06:31.360 align:start position:0% then we would typically label these 00:06:31.360 --> 00:06:33.430 align:start position:0% then we would typically label these factors this would be labeled social 00:06:33.430 --> 00:06:33.440 align:start position:0% factors this would be labeled social 00:06:33.440 --> 00:06:33.990 align:start position:0% factors this would be labeled social perception 00:06:33.990 --> 00:06:34.000 align:start position:0% perception 00:06:34.000 --> 00:06:35.830 align:start position:0% perception this would be labeled uh social 00:06:35.830 --> 00:06:35.840 align:start position:0% this would be labeled uh social 00:06:35.840 --> 00:06:38.790 align:start position:0% this would be labeled uh social adaptability and so on 00:06:38.790 --> 00:06:38.800 align:start position:0% adaptability and so on 00:06:38.800 --> 00:06:41.029 align:start position:0% adaptability and so on so this is the tool that we use for 00:06:41.029 --> 00:06:41.039 align:start position:0% so this is the tool that we use for 00:06:41.039 --> 00:06:43.029 align:start position:0% so this is the tool that we use for validating items empirically 00:06:43.029 --> 00:06:43.039 align:start position:0% validating items empirically 00:06:43.039 --> 00:06:45.590 align:start position:0% validating items empirically how do we access reliability once we 00:06:45.590 --> 00:06:45.600 align:start position:0% how do we access reliability once we 00:06:45.600 --> 00:06:47.270 align:start position:0% how do we access reliability once we have established that items measure 00:06:47.270 --> 00:06:47.280 align:start position:0% have established that items measure 00:06:47.280 --> 00:06:48.390 align:start position:0% have established that items measure something in common 00:06:48.390 --> 00:06:48.400 align:start position:0% something in common 00:06:48.400 --> 00:06:50.870 align:start position:0% something in common by using factor analysis we calculate 00:06:50.870 --> 00:06:50.880 align:start position:0% by using factor analysis we calculate 00:06:50.880 --> 00:06:52.390 align:start position:0% by using factor analysis we calculate coefficient alpha 00:06:52.390 --> 00:06:52.400 align:start position:0% coefficient alpha 00:06:52.400 --> 00:06:54.469 align:start position:0% coefficient alpha how exactly it's calculated it's not 00:06:54.469 --> 00:06:54.479 align:start position:0% how exactly it's calculated it's not 00:06:54.479 --> 00:06:55.670 align:start position:0% how exactly it's calculated it's not useful to know 00:06:55.670 --> 00:06:55.680 align:start position:0% useful to know 00:06:55.680 --> 00:06:58.469 align:start position:0% useful to know but uh it basically calculates the 00:06:58.469 --> 00:06:58.479 align:start position:0% but uh it basically calculates the 00:06:58.479 --> 00:06:59.749 align:start position:0% but uh it basically calculates the reliability of 00:06:59.749 --> 00:06:59.759 align:start position:0% reliability of 00:06:59.759 --> 00:07:02.469 align:start position:0% reliability of the average or the sum of items that 00:07:02.469 --> 00:07:02.479 align:start position:0% the average or the sum of items that 00:07:02.479 --> 00:07:04.070 align:start position:0% the average or the sum of items that belong to the same scale 00:07:04.070 --> 00:07:04.080 align:start position:0% belong to the same scale 00:07:04.080 --> 00:07:07.270 align:start position:0% belong to the same scale so if we take the integration on 00:07:07.270 --> 00:07:07.280 align:start position:0% so if we take the integration on 00:07:07.280 --> 00:07:09.830 align:start position:0% so if we take the integration on scale here it has four items we take a 00:07:09.830 --> 00:07:09.840 align:start position:0% scale here it has four items we take a 00:07:09.840 --> 00:07:11.589 align:start position:0% scale here it has four items we take a sum of those four items 00:07:11.589 --> 00:07:11.599 align:start position:0% sum of those four items 00:07:11.599 --> 00:07:14.950 align:start position:0% sum of those four items then the alpha here tells us what would 00:07:14.950 --> 00:07:14.960 align:start position:0% then the alpha here tells us what would 00:07:14.960 --> 00:07:16.629 align:start position:0% then the alpha here tells us what would be the reliability of 00:07:16.629 --> 00:07:16.639 align:start position:0% be the reliability of 00:07:16.639 --> 00:07:20.070 align:start position:0% be the reliability of that sum typically values greater than 00:07:20.070 --> 00:07:20.080 align:start position:0% that sum typically values greater than 00:07:20.080 --> 00:07:22.950 align:start position:0% that sum typically values greater than 0.7 are considered acceptable 00:07:22.950 --> 00:07:22.960 align:start position:0% 0.7 are considered acceptable 00:07:22.960 --> 00:07:25.670 align:start position:0% 0.7 are considered acceptable but oftentimes we get higher sometimes 00:07:25.670 --> 00:07:25.680 align:start position:0% but oftentimes we get higher sometimes 00:07:25.680 --> 00:07:26.469 align:start position:0% but oftentimes we get higher sometimes we get lower 00:07:26.469 --> 00:07:26.479 align:start position:0% we get lower 00:07:26.479 --> 00:07:29.110 align:start position:0% we get lower and sometimes lower reliability can be 00:07:29.110 --> 00:07:29.120 align:start position:0% and sometimes lower reliability can be 00:07:29.120 --> 00:07:29.670 align:start position:0% and sometimes lower reliability can be uh 00:07:29.670 --> 00:07:29.680 align:start position:0% uh 00:07:29.680 --> 00:07:31.589 align:start position:0% uh okay if your question is something that 00:07:31.589 --> 00:07:31.599 align:start position:0% okay if your question is something that 00:07:31.599 --> 00:07:33.510 align:start position:0% okay if your question is something that hasn't been never asked that before 00:07:33.510 --> 00:07:33.520 align:start position:0% hasn't been never asked that before 00:07:33.520 --> 00:07:35.589 align:start position:0% hasn't been never asked that before if you're studying something that has 00:07:35.589 --> 00:07:35.599 align:start position:0% if you're studying something that has 00:07:35.599 --> 00:07:37.670 align:start position:0% if you're studying something that has very well established scales 00:07:37.670 --> 00:07:37.680 align:start position:0% very well established scales 00:07:37.680 --> 00:07:40.710 align:start position:0% very well established scales then uh we might require 0.85 0.9 00:07:40.710 --> 00:07:40.720 align:start position:0% then uh we might require 0.85 0.9 00:07:40.720 --> 00:07:43.029 align:start position:0% then uh we might require 0.85 0.9 reliability because we we are the 00:07:43.029 --> 00:07:43.039 align:start position:0% reliability because we we are the 00:07:43.039 --> 00:07:45.110 align:start position:0% reliability because we we are the baseline so high already 00:07:45.110 --> 00:07:45.120 align:start position:0% baseline so high already 00:07:45.120 --> 00:07:47.430 align:start position:0% baseline so high already so let's take a summary of measurement 00:07:47.430 --> 00:07:47.440 align:start position:0% so let's take a summary of measurement 00:07:47.440 --> 00:07:49.189 align:start position:0% so let's take a summary of measurement the important concept of investment is 00:07:49.189 --> 00:07:49.199 align:start position:0% the important concept of investment is 00:07:49.199 --> 00:07:51.189 align:start position:0% the important concept of investment is reliability lack of random noise in our 00:07:51.189 --> 00:07:51.199 align:start position:0% reliability lack of random noise in our 00:07:51.199 --> 00:07:51.909 align:start position:0% reliability lack of random noise in our measures 00:07:51.909 --> 00:07:51.919 align:start position:0% measures 00:07:51.919 --> 00:07:53.990 align:start position:0% measures validity do the variables actually 00:07:53.990 --> 00:07:54.000 align:start position:0% validity do the variables actually 00:07:54.000 --> 00:07:55.350 align:start position:0% validity do the variables actually measure what they are supposed to 00:07:55.350 --> 00:07:55.360 align:start position:0% measure what they are supposed to 00:07:55.360 --> 00:07:56.230 align:start position:0% measure what they are supposed to measure 00:07:56.230 --> 00:07:56.240 align:start position:0% measure 00:07:56.240 --> 00:07:58.790 align:start position:0% measure reliability is conceptually easy to 00:07:58.790 --> 00:07:58.800 align:start position:0% reliability is conceptually easy to 00:07:58.800 --> 00:08:00.070 align:start position:0% reliability is conceptually easy to demonstrate and vertically 00:08:00.070 --> 00:08:00.080 align:start position:0% demonstrate and vertically 00:08:00.080 --> 00:08:02.950 align:start position:0% demonstrate and vertically you just take uh repeated measures using 00:08:02.950 --> 00:08:02.960 align:start position:0% you just take uh repeated measures using 00:08:02.960 --> 00:08:04.150 align:start position:0% you just take uh repeated measures using the same instrument if the 00:08:04.150 --> 00:08:04.160 align:start position:0% the same instrument if the 00:08:04.160 --> 00:08:06.950 align:start position:0% the same instrument if the correlated is reliable with measuring 00:08:06.950 --> 00:08:06.960 align:start position:0% correlated is reliable with measuring 00:08:06.960 --> 00:08:08.390 align:start position:0% correlated is reliable with measuring people and their attitudes and 00:08:08.390 --> 00:08:08.400 align:start position:0% people and their attitudes and 00:08:08.400 --> 00:08:10.150 align:start position:0% people and their attitudes and perceptions this is difficult because 00:08:10.150 --> 00:08:10.160 align:start position:0% perceptions this is difficult because 00:08:10.160 --> 00:08:11.589 align:start position:0% perceptions this is difficult because the person remembers 00:08:11.589 --> 00:08:11.599 align:start position:0% the person remembers 00:08:11.599 --> 00:08:13.749 align:start position:0% the person remembers what they answered in the past so in 00:08:13.749 --> 00:08:13.759 align:start position:0% what they answered in the past so in 00:08:13.759 --> 00:08:15.909 align:start position:0% what they answered in the past so in practice we have to use multiple 00:08:15.909 --> 00:08:15.919 align:start position:0% practice we have to use multiple 00:08:15.919 --> 00:08:18.710 align:start position:0% practice we have to use multiple questions that are slightly different to 00:08:18.710 --> 00:08:18.720 align:start position:0% questions that are slightly different to 00:08:18.720 --> 00:08:19.909 align:start position:0% questions that are slightly different to do that 00:08:19.909 --> 00:08:19.919 align:start position:0% do that 00:08:19.919 --> 00:08:22.550 align:start position:0% do that and then we calculate coefficient out 00:08:22.550 --> 00:08:22.560 align:start position:0% and then we calculate coefficient out 00:08:22.560 --> 00:08:23.589 align:start position:0% and then we calculate coefficient out validity 00:08:23.589 --> 00:08:23.599 align:start position:0% validity 00:08:23.599 --> 00:08:24.950 align:start position:0% validity is something that we can only 00:08:24.950 --> 00:08:24.960 align:start position:0% is something that we can only 00:08:24.960 --> 00:08:27.350 align:start position:0% is something that we can only demonstrate less directly in practice 00:08:27.350 --> 00:08:27.360 align:start position:0% demonstrate less directly in practice 00:08:27.360 --> 00:08:30.550 align:start position:0% demonstrate less directly in practice uh validity is an argument for it 00:08:30.550 --> 00:08:30.560 align:start position:0% uh validity is an argument for it 00:08:30.560 --> 00:08:32.949 align:start position:0% uh validity is an argument for it that we have to make on conceptual 00:08:32.949 --> 00:08:32.959 align:start position:0% that we have to make on conceptual 00:08:32.959 --> 00:08:33.670 align:start position:0% that we have to make on conceptual grounds 00:08:33.670 --> 00:08:33.680 align:start position:0% grounds 00:08:33.680 --> 00:08:36.790 align:start position:0% grounds for example if we use co gender as a cs 00:08:36.790 --> 00:08:36.800 align:start position:0% for example if we use co gender as a cs 00:08:36.800 --> 00:08:38.310 align:start position:0% for example if we use co gender as a cs name as a measure of gender 00:08:38.310 --> 00:08:38.320 align:start position:0% name as a measure of gender 00:08:38.320 --> 00:08:41.190 align:start position:0% name as a measure of gender we have to under or grounds argue that 00:08:41.190 --> 00:08:41.200 align:start position:0% we have to under or grounds argue that 00:08:41.200 --> 00:08:43.110 align:start position:0% we have to under or grounds argue that name is a good measure of gender 00:08:43.110 --> 00:08:43.120 align:start position:0% name is a good measure of gender 00:08:43.120 --> 00:08:45.110 align:start position:0% name is a good measure of gender it's pretty obvious for most people that 00:08:45.110 --> 00:08:45.120 align:start position:0% it's pretty obvious for most people that 00:08:45.120 --> 00:08:47.110 align:start position:0% it's pretty obvious for most people that that would be a valid measure 00:08:47.110 --> 00:08:47.120 align:start position:0% that would be a valid measure 00:08:47.120 --> 00:08:49.269 align:start position:0% that would be a valid measure empirically when we have multiple items 00:08:49.269 --> 00:08:49.279 align:start position:0% empirically when we have multiple items 00:08:49.279 --> 00:08:50.310 align:start position:0% empirically when we have multiple items we can apply 00:08:50.310 --> 00:08:50.320 align:start position:0% we can apply 00:08:50.320 --> 00:08:53.030 align:start position:0% we can apply factor analysis to demonstrate that 00:08:53.030 --> 00:08:53.040 align:start position:0% factor analysis to demonstrate that 00:08:53.040 --> 00:08:53.509 align:start position:0% factor analysis to demonstrate that those 00:08:53.509 --> 00:08:53.519 align:start position:0% those 00:08:53.519 --> 00:08:55.750 align:start position:0% those indicators that are supposed to measure 00:08:55.750 --> 00:08:55.760 align:start position:0% indicators that are supposed to measure 00:08:55.760 --> 00:08:56.949 align:start position:0% indicators that are supposed to measure the same thing 00:08:56.949 --> 00:08:56.959 align:start position:0% the same thing 00:08:56.959 --> 00:08:58.550 align:start position:0% the same thing also have something in common 00:08:58.550 --> 00:08:58.560 align:start position:0% also have something in common 00:08:58.560 --> 00:09:00.790 align:start position:0% also have something in common empirically and then we assume that 00:09:00.790 --> 00:09:00.800 align:start position:0% empirically and then we assume that 00:09:00.800 --> 00:09:02.470 align:start position:0% empirically and then we assume that what they have in common is actually 00:09:02.470 --> 00:09:02.480 align:start position:0% what they have in common is actually 00:09:02.480 --> 00:09:04.310 align:start position:0% what they have in common is actually that they measure the same thing 00:09:04.310 --> 00:09:04.320 align:start position:0% that they measure the same thing 00:09:04.320 --> 00:09:06.790 align:start position:0% that they measure the same thing in practice using coefficient alpha and 00:09:06.790 --> 00:09:06.800 align:start position:0% in practice using coefficient alpha and 00:09:06.800 --> 00:09:08.150 align:start position:0% in practice using coefficient alpha and factor analysis 00:09:08.150 --> 00:09:08.160 align:start position:0% factor analysis 00:09:08.160 --> 00:09:10.870 align:start position:0% factor analysis is what most of the articles that apply 00:09:10.870 --> 00:09:10.880 align:start position:0% is what most of the articles that apply 00:09:10.880 --> 00:09:14.480 align:start position:0% is what most of the articles that apply survey data do this